© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 74516
    Prev
    Next
    INDEX
    Explanations

    take your time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     însă
    0.47
     enteros
    0.42
    mapsto
    0.40
    த்தான்
    0.39
     cáps
    0.38
    த்தான
    0.38
     具体
    0.38
    낍
    0.38
    speak
    0.36
     행동
    0.36
    POSITIVE LOGITS
    From
    0.45
     eman
    0.41
    inburgh
    0.39
     From
    0.37
     attorney
    0.36
    റും
    0.36
    force
    0.36
    velopper
    0.35
     Vert
    0.35
    ’.
    0.35
    Activations Density 0.001%

    No Known Activations